A new learning algorithm for feed-forward neural networks based on linear programming is introduced. This alternative to back-propagation gives faster and more reliable learning on reasonably sized examples. Extensions of the method for efficient (approximate) implementations in large networks are considered.

Handwritten character recognition plays an important role in the modern world. It can solve more complex problems and makes human’s job easier. The present paper portrays a novel approach in recognizing handwritten devanagari character through feed forward back propagation neural network. All the experiments are conducted by using the Artificial Neural Network tool of Matlab.

We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, an...

John A. Hertz Nordita Blegdamsvej 17 2100 Copenhagen Denmark We introduce a cost function for learning in feed-forward neural networks which is an explicit function of the internal representation in addition to the weights. The learning problem can then be formulated as two simple perceptrons and a search for internal representations. Back-propagation is recovered as a limit. The frequency of s...

In this paper, we adapt the classical learning algorithm for feed-forward neural networks when monotonicity is require in the input-output mapping. Such requirements arise, for instance, when prior knowledge of the process being observed is available. Monotonicity can be imposed by the addition of suitable penalization terms to the error function. The objective function, however, depends nonlin...

This paper presents a method of recognition of isolated offline handwritten Devanagari numerals using wavelets and neural network classifier. This method of optical character recognition takes the handwritten numeral image as input. After pre-processing, it is subjected to single level wavelet decomposition using Daubechies-4 wavelet filter. This wavelet decomposition allows viewing the input n...

This paper presents the use of ANN as a pattern classifier for differential protection of power transformer, which makes the discrimination among normal, magnetizing inrush, over-excitation, external fault and internal fault currents. The Back Propagation Neural Network Algorithm and Genetic Algorithm are used to train the multi-layered feed forward neural network and simulated results are comp...

This paper proposes to extend the band width of narrow band telephone speech signal by employing feed forward back propagation neural network. There are different types of faster training algorithm are available in the literature like Variable Learning Rate, Resilient Back propagation, Polak-Ribiére Conjugate Gradient , Conjugate Gradient with Powell/Beale Restarts , BFGS Quasi-Newton , One-Ste...

Back propagation algorithm (BPA) have the complexity, local minima problem so we are using Particle Swarm optimization (PSO) algorithms to reduce and optimize BPA. In this paper, two variants of Particle Swarm Optimization (PSO) PSO_Hill and PSO_A* is used as optimization algorithm. PSO_Hill and PSO_A* algorithms are analyzed and evaluated on the basis of their advantages, applied to feed forwa...

This paper proposes to extend the band width of narrow band telephone speech signal by employing feed forward back propagation neural network. There are different types of faster training algorithm are available in the literature like Variable Learning Rate, Resilient Back propagation, Polak-Ribiére Conjugate Gradient , Conjugate Gradient with Powell/Beale Restarts , BFGS Quasi-Newton , One-Ste...